Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.9368. Min Act: -0.1700
Data Index: 7972565 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.7180. Min Act: -0.1700
Data Index: 7174641 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.7180. Min Act: -0.1700
Data Index: 1704436 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.6868. Min Act: -0.1700
Data Index: 8235749 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.5305. Min Act: -0.1700
Data Index: 3443459 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.4993. Min Act: -0.1700
Data Index: 672478 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.4680. Min Act: -0.1700
Data Index: 2104356 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.4680. Min Act: -0.1700
Data Index: 546639 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.4368. Min Act: -0.1700
Data Index: 4598694 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.4368. Min Act: -0.1700
Data Index: 634483 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.4368. Min Act: -0.1700
Data Index: 8644948 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.3743. Min Act: -0.1700
Data Index: 687005 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.3743. Min Act: -0.1700
Data Index: 8445145 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.3743. Min Act: -0.1700
Data Index: 7970643 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.3430. Min Act: -0.1700
Data Index: 5520994 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.3430. Min Act: -0.1700
Data Index: 2226955 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.3430. Min Act: -0.1700
Data Index: 580015 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.3430. Min Act: -0.1700
Data Index: 5142037 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.3118. Min Act: -0.1700
Data Index: 1538499 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9368. Min Range: -6.9368
Max Act: 6.3118. Min Act: -0.1700
Data Index: 787554 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19